Optimizely Connector for AI agents.
10 live capabilities
Manage A/B tests and feature flags through conversational commands.
Waiting for input…
Why people use Optimizely
Optimizely for Faster Experimentation Management
With this Connector, you just ask your agent to do the work. You can pull a summary of all projects or check the status of a specific test in one go. It keeps you in your flow and lets you focus on the results instead of the navigation.
What Vinkius changes
You get instant, conversational control over your experimentation and feature management.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Emergency test shutdown
A growth engineer notices a bug in a live test and asks the agent to use pause_experiment to stop the test immediately.
- Real-world use case 02
Feature flag audit
A PM wants to ensure a new feature flag is correctly scoped and uses get_feature_flag to check the definition before a release.
- Real-world use case 03
New team onboarding
A new team member joins and asks the agent to list_projects to see the history of experiments and projects in the account.
Complete set · 10capabilities
The complete Optimizely capability set.
These are the exact actions your AI can choose when you ask it to work with Optimizely.
01—04
4 capabilities in this set.
Part of 10 available through Optimizely.
- 01 Capability
List feature flags
List every feature flag associated with a project. Use this to see what's currently toggled.
- 02 Capability
Get experiment
Get specific details for a single experiment. Use this to check the exact configuration of a test.
- 03 Capability
Get feature flag
Pull the definition and status of a specific feature flag. This helps you verify if a flag is active.
- 04 Capability
Get project
Retrieve detailed metadata for a specific Optimizely project. Use it to see project-level settings.
05—07
3 capabilities in this set.
Part of 10 available through Optimizely.
- 05 Capability
List audiences
Show all defined audiences within a specific project. This is useful for auditing your targeting rules.
- 06 Capability
List events
List all conversion events tied to a project. Use this to verify your tracking setup.
- 07 Capability
List experiments
Show all experiments currently in a project. This gives you a quick overview of your active tests.
08—10
3 capabilities in this set.
Part of 10 available through Optimizely.
- 08 Capability
List projects
Show a complete list of all Optimizely projects in your account. This helps you see your whole workspace.
- 09 Capability
Pause experiment
Set an experiment's status to paused immediately. Use this to stop a test if you notice an issue.
- 10 Capability
Start experiment
Set an experiment's status to running. This lets you launch a test through a simple command.
Set up in minutes
One URL. Then ask Optimizely to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Optimizely from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_bvFb0C3kWGnKUOKniHIrp2EkQUMOnHphRVl70b9H/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Optimizely, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Optimizely for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_bvFb0C3kWGnKUOKniHIrp2EkQUMOnHphRVl70b9H/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Optimizely URL.
- Step 03
Save and start
Save the connection and enable Optimizely in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"optimizely": {
"url": "https://edge.vinkius.com/vk_preview_bvFb0C3kWGnKUOKniHIrp2EkQUMOnHphRVl70b9H/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Optimizely
Open Agent mode in chat and ask: "Using Optimizely, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"optimizely": {
"url": "https://edge.vinkius.com/vk_preview_bvFb0C3kWGnKUOKniHIrp2EkQUMOnHphRVl70b9H/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Optimizely
Ask Copilot: "Using Optimizely, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"optimizely": {
"url": "https://edge.vinkius.com/vk_preview_bvFb0C3kWGnKUOKniHIrp2EkQUMOnHphRVl70b9H/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Optimizely
Open Cascade and ask: "Using Optimizely, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"optimizely": {
"url": "https://edge.vinkius.com/vk_preview_bvFb0C3kWGnKUOKniHIrp2EkQUMOnHphRVl70b9H/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Optimizely
Ask Cline: "Using Optimizely, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add optimizely --transport http "https://edge.vinkius.com/vk_preview_bvFb0C3kWGnKUOKniHIrp2EkQUMOnHphRVl70b9H/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Optimizely
Ask Claude: "Using Optimizely, show me...". 10 tools are ready
Where the request belongs
Work Optimizely can move forward.
This is for the product team tired of the dashboard fatigue that comes with managing complex A/B tests and high-velocity feature releases.
Product Manager
Checking the status of a live experiment during a sprint review without leaving the chat.
Growth Engineer
Auditing audience definitions and event triggers during a production hotfix.
Data Scientist
Pulling experiment metadata to verify tracking setup for a new analysis task.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsGrowthBook
Manage feature flags and experiments via GrowthBook. control environments, toggle features, and organize projects directly from your AI agent.
Statsig
Manage feature flags, dynamic configs, and experiments. Evaluate gates and log events directly from your AI agent.
Kameleoon
Manage A/B testing, personalization, and experimentation workflows via AI agents.
PostHog
Analyze product data via PostHog. list insights, track persons, inspect feature flags, and monitor experiments directly from any AI agent.
Flipt
Manage feature flags and rollouts via Flipt. list namespaces, flags, segments, and rules directly from your AI agent.
DevCycle
Equip your AI agent to manage feature flags, monitor environments, and track variations via the DevCycle API.
Bring your own AI
Change the model, client or framework. Keep Optimizely connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Optimizely.
The practical details behind the request, access and result.
How can the Optimizely MCP help my growth team?
It gives your team a way to check experiment statuses and toggle features using natural language. This means you can get answers faster without constantly switching between your AI client and the Optimizely dashboard.
Can I use the Optimizely MCP to stop a live test?
Yes, you can ask your agent to pause an experiment immediately. This is helpful for quickly responding to issues during a live rollout.
Does the Optimizely MCP show me my audience targeting?
Yes, you can use the Connector to list the defined audiences in any project. This helps you verify your targeting rules quickly.
How do I connect Optimizely to my AI agent?
You just need to subscribe to the Connector on Vinkius and add your Optimizely Personal Access Token to your agent's configuration.
Can the Optimizely MCP list all my active projects?
Yes, your agent can pull a full list of all projects in your account so you can see your entire workspace at a glance.
Will the Optimizely MCP help me audit feature flags?
Absolutely. You can ask your agent to pull the definitions and statuses of flags across different projects to ensure everything is set up correctly.
Where do I find my Personal Access Token?
In Optimizely, go to Profile Settings > API Access and generate a new Personal Access Token. Ensure it has the necessary permissions for the projects you want to manage.
Can I start an experiment that is in draft mode?
Yes, using the start_experiment capability will attempt to set the status to 'running'. However, Optimizely requires the experiment to be valid and fully configured before it can transition from draft to running.
How do I find my Project ID?
You can use the list_projects capability to see all projects associated with your account along with their IDs. You can also find it in the URL when viewing a project in the Optimizely dashboard.
One connection away
Give your agent a direct line to Optimizely.
Connect Optimizely once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available